Optimizing Average Reward Using Discounted Rewards

Kakade. "Optimizing Average Reward Using Discounted Rewards." Annual Conference on Computational Learning Theory, 2001. doi:10.1007/3-540-44581-1_40

[Kakade. "Optimizing Average Reward Using Discounted Rewards." Annual Conference on Computational Learning Theory, 2001.](https://mlanthology.org/colt/2001/kakade2001colt-optimizing/) doi:10.1007/3-540-44581-1_40

@inproceedings{kakade2001colt-optimizing,
  title     = {{Optimizing Average Reward Using Discounted Rewards}},
  author    = {Kakade, Sham M.},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2001},
  pages     = {605-615},
  doi       = {10.1007/3-540-44581-1_40},
  url       = {https://mlanthology.org/colt/2001/kakade2001colt-optimizing/}
}